[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-5689":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":16,"forks30d":16,"starsTrendScore":19,"compositeScore":20,"rankGlobal":10,"rankLanguage":10,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":24,"hasPages":22,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":36,"readmeContent":37,"aiSummary":38,"trendingCount":16,"starSnapshotCount":16,"syncStatus":17,"lastSyncTime":39,"discoverSource":40},5689,"deepreasoning","winfunc\u002Fdeepreasoning","winfunc","A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.","",null,"Rust",5353,441,45,50,0,2,6,1,65.54,"MIT License",false,"main",true,[26,27,28,29,30,31,32,33,34,35],"ai","anthropic","anthropic-claude","api","chain-of-thought","claude","deepseek","deepseek-r1","llm","rust","2026-06-12 04:00:26","\u003Cdiv align=\"center\">\n\n\u003Ch1>DeepReasoning 🐬🧠\u003C\u002Fh1>\n\n\u003Cimg src=\"frontend\u002Fpublic\u002Fdeepreasoning.png\" width=\"300\">\n\nHarness the power of DeepSeek R1's reasoning and Claude's creativity and code generation capabilities with a unified API and chat interface.\n\n[![GitHub license](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fgetasterisk\u002Fdeepreasoning)](https:\u002F\u002Fgithub.com\u002Fgetasterisk\u002Fdeepreasoning\u002Fblob\u002Fmain\u002FLICENSE.md)\n[![Rust](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Frust-v1.75%2B-orange)](https:\u002F\u002Fwww.rust-lang.org\u002F)\n[![API Status](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FAPI-Stable-green)](https:\u002F\u002Fdeepreasoning.asterisk.so)\n\n[Getting Started](#getting-started) •\n[Features](#features) •\n[API Usage](#api-usage) •\n[Documentation](#documentation) •\n[Self-Hosting](#self-hosting) •\n[Contributing](#contributing)\n\n---\n\n> [!NOTE]\n> **Disclaimer:** This project is not affiliated with, endorsed by, or sponsored by Anthropic. Claude is a trademark of Anthropic, PBC. This is an independent developer project using Claude.\n\n\u003C\u002Fdiv>\n\n## Table of Contents\n- [Overview](#overview)\n- [Features](#features)\n- [Why R1 + Claude?](#why-r1--claude)\n- [Getting Started](#getting-started)\n  - [Prerequisites](#prerequisites)\n  - [Installation](#installation)\n  - [Configuration](#configuration)\n- [API Usage](#api-usage)\n  - [Basic Example](#basic-example)\n  - [Streaming Example](#streaming-example)\n- [Configuration Options](#configuration-options)\n- [Self-Hosting](#self-hosting)\n- [Security](#security)\n- [Contributing](#contributing)\n- [License](#license)\n- [Acknowledgments](#acknowledgments)\n\n## Overview\n\nDeepReasoning is a high-performance LLM inference API that combines DeepSeek R1's Chain of Thought (CoT) reasoning capabilities with Anthropic Claude's creative and code generation prowess. It provides a unified interface for leveraging the strengths of both models while maintaining complete control over your API keys and data.\n\n## Features\n\n🚀 **Zero Latency** - Instant responses with R1's CoT followed by Claude's response in a single stream, powered by a high-performance Rust API\n\n🔒 **Private & Secure** - End-to-end security with local API key management. Your data stays private\n\n⚙️ **Highly Configurable** - Customize every aspect of the API and interface to match your needs\n\n🌟 **Open Source** - Free and open-source codebase. Contribute, modify, and deploy as you wish\n\n🤖 **Dual AI Power** - Combine DeepSeek R1's reasoning with Claude's creativity and code generation\n\n🔑 **Managed BYOK API** - Use your own API keys with our managed infrastructure for complete control\n\n## Why R1 + Claude?\n\nDeepSeek R1's CoT trace demonstrates deep reasoning to the point of an LLM experiencing \"metacognition\" - correcting itself, thinking about edge cases, and performing quasi Monte Carlo Tree Search in natural language.\n\nHowever, R1 lacks in code generation, creativity, and conversational skills. Claude 3.5 Sonnet excels in these areas, making it the perfect complement. DeepReasoning combines both models to provide:\n\n- R1's exceptional reasoning and problem-solving capabilities\n- Claude's superior code generation and creativity\n- Fast streaming responses in a single API call\n- Complete control with your own API keys\n\n## Getting Started\n\n### Prerequisites\n\n- Rust 1.75 or higher\n- DeepSeek API key\n- Anthropic API key\n\n### Installation\n\n1. Clone the repository:\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fgetasterisk\u002Fdeepreasoning.git\ncd deepreasoning\n```\n\n2. Build the project:\n```bash\ncargo build --release\n```\n\n### Configuration\n\nCreate a `config.toml` file in the project root:\n\n```toml\n[server]\nhost = \"127.0.0.1\"\nport = 3000\n\n[pricing]\n# Configure pricing settings for usage tracking\n```\n\n## API Usage\n\nSee [API Docs](https:\u002F\u002Fdeepreasoning.chat)\n\n### Basic Example\n\n```python\nimport requests\n\nresponse = requests.post(\n    \"http:\u002F\u002F127.0.0.1:1337\u002F\",\n    headers={\n        \"X-DeepSeek-API-Token\": \"\u003CYOUR_DEEPSEEK_API_KEY>\",\n        \"X-Anthropic-API-Token\": \"\u003CYOUR_ANTHROPIC_API_KEY>\"\n    },\n    json={\n        \"messages\": [\n            {\"role\": \"user\", \"content\": \"How many 'r's in the word 'strawberry'?\"}\n        ]\n    }\n)\n\nprint(response.json())\n```\n\n### Streaming Example\n\n```python\nimport asyncio\nimport json\nimport httpx\n\nasync def stream_response():\n    async with httpx.AsyncClient() as client:\n        async with client.stream(\n            \"POST\",\n            \"http:\u002F\u002F127.0.0.1:1337\u002F\",\n            headers={\n                \"X-DeepSeek-API-Token\": \"\u003CYOUR_DEEPSEEK_API_KEY>\",\n                \"X-Anthropic-API-Token\": \"\u003CYOUR_ANTHROPIC_API_KEY>\"\n            },\n            json={\n                \"stream\": True,\n                \"messages\": [\n                    {\"role\": \"user\", \"content\": \"How many 'r's in the word 'strawberry'?\"}\n                ]\n            }\n        ) as response:\n            response.raise_for_status()\n            async for line in response.aiter_lines():\n                if line:\n                    if line.startswith('data: '):\n                        data = line[6:]\n                        try:\n                            parsed_data = json.loads(data)\n                            if 'content' in parsed_data:\n                                content = parsed_data.get('content', '')[0]['text']\n                                print(content, end='',flush=True)\n                            else:\n                                print(data, flush=True)\n                        except json.JSONDecodeError:\n                            pass\n\nif __name__ == \"__main__\":\n    asyncio.run(stream_response())\n```\n\n## Configuration Options\n\nThe API supports extensive configuration through the request body:\n\n```json\n{\n    \"stream\": false,\n    \"verbose\": false,\n    \"system\": \"Optional system prompt\",\n    \"messages\": [...],\n    \"deepseek_config\": {\n        \"headers\": {},\n        \"body\": {}\n    },\n    \"anthropic_config\": {\n        \"headers\": {},\n        \"body\": {}\n    }\n}\n```\n\n## Self-Hosting\n\nDeepReasoning can be self-hosted on your own infrastructure. Follow these steps:\n\n1. Configure environment variables or `config.toml`\n2. Build the Docker image or compile from source\n3. Deploy to your preferred hosting platform\n\n## Security\n\n- No data storage or logged\n- BYOK (Bring Your Own Keys) architecture\n- Regular security audits and updates\n\n## Contributing\n\nWe welcome contributions! Please see our [Contributing Guidelines](CONTRIBUTING.md) for details on:\n\n- Code of Conduct\n- Development process\n- Submitting pull requests\n- Reporting issues\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE.md) file for details.\n\n## Acknowledgments\n\nDeepReasoning is a free and open-source project by [Asterisk](https:\u002F\u002Fasterisk.so\u002F). Special thanks to:\n\n- DeepSeek for their incredible R1 model\n- Anthropic for Claude's capabilities\n- The open-source community for their continuous support\n\n---\n\n\u003Cdiv align=\"center\">\nMade with ❤️ by \u003Ca href=\"https:\u002F\u002Fasterisk.so\">Asterisk\u003C\u002Fa>\n\u003C\u002Fdiv>","DeepReasoning 是一个高性能的LLM推理API和聊天界面，集成了DeepSeek R1的链式思维（CoT）推理能力和Anthropic Claude模型的创造力与代码生成能力。该项目使用Rust语言开发，确保了低延迟和高安全性，同时支持本地API密钥管理和高度可配置性。它适合需要结合强大推理能力和创造性输出的应用场景，如复杂的对话系统、代码辅助生成以及任何需要深度分析与创意内容生成相结合的任务。通过提供统一的接口，用户可以充分利用这两种模型的优势，同时保持对自己数据和API密钥的完全控制。","2026-06-11 03:04:42","top_language"]